How could we get the "p0_z" for the kl loss?

autonomousvision / occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"

MIT License

1.48k stars 291 forks source link

Open XiaoyanQian opened 1 year ago

XiaoyanQian commented 1 year ago

Hi, could you help to figure out the p0_z for KL loss in the following code:

kl = dist.kl_divergence(q_z, self.model.p0_z).sum(dim=-1) loss = kl.mean()

How can I get the p0_z? Any thoughts?